Evolutionary behavior learning for action-based environment modeling by a mobile robot

This paper describes an evolutionary way to lean behaviors of a mobile robot for recognizing environments. We have proposed AEM (Action-based Environment Modeling) which is an appropriate approach for a simple mobile robot to recognize environments, and made experiments using a real robot. The suitable behaviors for AEM have been described by a human designer. However the design is very difficult for them because of the huge search space. Thus we propose the evolutionary design method of such behaviors using genetic algorithm and make experiments in which a robot recognizes the environments with different structures. As results, we found out that the evolutionary approach is promising to automatically acquire behaviors for AEM.

For educational purposes there is a need to teach electrical and computer engineering students the basics of the design of state machines using programmable logic devices, and for students interested in mobile robots to teach them the basics of mobile robots' behaviors. At the same time one of the topics of interest in the mobile robot's community is how to generate their new behaviors, using state machines, automatically. This paper discusses how to create mobile robots' behaviors using genetic algorithms (GAs), implementing them in programmable logic devices (FPGAs) and how these behaviors can be programmed by students in a mobile robotics course. The behaviors are encoded as algorithm state machines and using feed-forward artificial neural networks (ANN). In the state-machine approach, each individual's chromosome represents, given a set of inputs coming from the sensors and the current state, both the next state and the outputs that control the robot's movements. In the ANN approach, whose weights are found also with GAs, a pipeline architecture was built to perform it, each pipeline executes a layer of the ANN, thus once the pipeline is full the execution speed of the ANN is one sensors' clock cycle. We evaluate the behaviors generated by the GA according to a fitness function that grades their performance for avoiding obstacles. The inputs to such a robot are infrared sensors to detect obstacles, the outputs are the velocities of its wheels. Our objectives are first, to prove that GAs are a good option as a method for finding behaviors for mobile robots' navigation, and second, that these behaviors can be implemented in an efficient way in FPGAs. We tested both behaviors in a small mobile robot, that is build in an electrical engineering course that teaches how to build mobile robots.

In this study, we present a socially aware navigation framework for mobile service robots by integrating the systems proposed in our previous studies into a completed mobile robot navigation system, including the human detection and tracking system that is used to detect and track humans; the encoder and laser-based localization and mapping system that is used to determine the position of the robot in the environment; the approaching pose estimation system that is used to estimate the approaching pose of the robot to the human; and the social timed elastic band-based motion planning system that is used to socially navigate the mobile robots to approach the human. In addition, in the paper we describe in detail the motor control system and the design of our mobile robot platform, which is then utilized to conduct experiments in the real-world environments. We verify the feasibility and usefulness of the proposed socially aware robot navigation framework through a series of experiments in a corridor-like environment. The experimental results show that our proposed framework is able to drive the mobile robots to both avoid and approach the humans, providing the safety and comfort for the humans and socially acceptable behaviors for the mobile service robots in the dynamic social environments.

To design behaviors of a mobile robot for realizing given tasks, a designer has to make a set of rules which generate a proper action from a state of sensors. In general, however, it is difficult that the designer makes all set of rules since the number of rules is very large and the proper action for a state of sensors is not clear. Many methods have been proposed to solve such a problem using reinforcement learning genetic programming or genetic algorithm and so on. However, those methods are not sufficiently applied to the case in which the environment changes or is unknown. In this paper, new method which is efficiently applied to such a difficult case is proposed. The proposed method is constructed by genetic algorithm and action rule-base. The experimental results, using a mobile robot simulator, shows that the mobile robot can properly act in the unknown environments.

Purpose– The purpose of this paper is to explore a novel control approach for swift and accurate positioning and tracking of a mobile robot. Coordinated movement of the mobile robot-body and chameleon-inspired binocular “negative correlation” visual system (CIBNCVS) with neck has rarely been considered in conventional mobile robot design. However, it is vital in swift and accurate positioning and tracking of the target. Consequently, it is valuable to find an optimized method where the robot-body, the biomimetic eyes and neck could achieve optimal coordinated movement.Design/methodology/approach– Based on a wheeled mobile robot, a biomimetic dual Pan–Tilt–Zoom visual system with neck is constructed. The cameras can rely on the unique “negative correlation” mode of chameleon vision, and cooperate with neck, achieving swift search of the 160° scope in front of the robot. Genetic algorithm is used to obtain optimal rotation of the neck and robot-body. Variable resolution targeting is also applied for accurate aiming. Using these two approaches, we can achieve efficient targeting with low energy consumption. Particle filter algorithm is further utilized for real-time tracking.Findings– In the proposed approach, swift and accurate positioning and tracking of the target can be obtained. The rationality of the approach is verified by experiments on flat and sandy terrains with satisfactory results.Originality/value– This paper proposes a novel control approach for wheeled mobile robots, which achieves coordinated movement of the robot-body and CIBNCVS with neck concerning time and energy saving in the process of swift and accurate tracking.

Object slip perception is essential for mobile manipulation robots to perform manipulation tasks reliably in the dynamic real-world. Traditional approaches to robot arms’ slip perception use tactile or vision sensors. However, mobile robots still have to deal with noise in their sensor signals caused by the robot’s movement in a changing environment. To solve this problem, we present an anomaly detection method that utilizes multisensory data based on a deep autoencoder model. The proposed framework integrates heterogeneous data streams collected from various robot sensors, including RGB and depth cameras, a microphone, and a force-torque sensor. The integrated data is used to train a deep autoencoder to construct latent representations of the multisensory data that indicate the normal status. Anomalies can then be identified by error scores measured by the difference between the trained encoder’s latent values and the latent values of reconstructed input data. In order to evaluate the proposed framework, we conducted an experiment that mimics an object slip by a mobile service robot operating in a real-world environment with diverse household objects and different moving patterns. The experimental results verified that the proposed framework reliably detects anomalies in object slip situations despite various object types and robot behaviors, and visual and auditory noise in the environment.

We present a neural network that learns to control approach and avoidance behaviors in a mobile robot based on a form of animal learning known as operant conditioning. Learning, which requires no supervision, takes place as the robot moves around an environment cluttered with obstacles and light sources. The neural network requires no knowledge of the geometry of the robot or of the quality, number, or configuration of the robot's sensors. In this article we provide a detailed presentation of the model, and show our results with the Khepera and Pioneer 1 mobile robots.

Purpose: The purpose of this paper is to describe the implementation of a Fleet Management System (FMS) that plans and controls the execution of logistics tasks by a set of mobile robots in a real-world hospital environment. The FMS is developed upon an architecture that hosts a routing engine, a task scheduler, an Endorse Broker, a controller and a backend Application Programming Interface (API). The routing engine handles the geo-referenced data and the calculation of routes; the task scheduler implements algorithms to solve the task allocation problem and the trolley loading problem using Integer Linear Programming (ILP) model and a Genetic Algorithm (GA) depending on the problem size. The Endorse Broker provides a messaging system to exchange information with the robotic fleet, while the controller implements the control rules to ensure the execution of the work plan. Finally, the Backend API exposes some FMS to external systems.Design/methodology/approach: The first part of the paper, focuses on the dynamic path planning problem of a set of mobile robots in indoor spaces such as hospitals, laboratories and shopping centres. A review of algorithms developed in the literature, to address dynamic path planning, is carried out; and an analysis of the applications of such algorithms in mobile robots that operate in real in-door spaces is performed. The second part of the paper focuses on the description of the FMS, which consists of five integrated tools to support the multi-robot dynamic path planning and the fleet management.Findings: The literature review, carried out in the context of path planning problem of multiple mobile robots in in-door spaces, has posed great challenges due to the environment characteristics in which robots move. The developed FMS for mobile robots in healthcare environments has resulted on a tool that enables to: (i) interpret of geo-referenced data; (ii) calculate and recalculate dynamic path plans and task execution plans, through the implementation of advanced algorithms that take into account dynamic events; (iii) track the tasks execution; (iv) fleet traffic control; and (v) to communicate with one another external systems.Practical implications: The proposed FMS has been developed under the scope of ENDORSE project that seeks to develop safe, efficient, and integrated indoor robotic fleets for logistic applications in healthcare and commercial spaces. Moreover, a computational analysis is performed using a virtual hospital floor-plant.Originality/value: This work proposes a novel FMS, which consists of integrated tools to support the mobile multi-robot dynamic path planning in a real-world hospital environment. These tools include: a routing engine that handles the geo-referenced data and the calculation of routes. A task scheduler that includes a mathematical model to solve the path planning problem, when a low number of robots is considered. In order to solve large size problems, a genetic algorithm is also implemented to compute the dynamic path planning with less computational effort. An Endorse broker to exchanges information between the robotic fleet and the FMS in a secure way. A backend API that provides interface to manage the master data of the FMS, to calculate an optimal assignment of a set of tasks to a group of robots to be executed on a specific date and time, and to add a new task to be executed in the current shift. Finally, a controller to ensures that the robots execute the tasks that have been assigned by the task scheduler.

In conducting their work in the industry quickly, precisely, and safely, mobile robots must be able to determine the position and direction of movement in their work environment. Several algorithms have been developed to solve maze rooms, however, when the room is huge with several obstacles which could be re-placed in other parts of the room, determining the path for a mobile robot will be difficult. This can be done by mapping the work environment and determining the position of the robot so that the robot has good path planning to get the optimal path. In this research, a Genetic Algorithm (GA) will be used to determine the fastest route that a robot may take when moving from one location to another. The method used is to design a mobile robot work environment, design genetic algorithm steps, create software for simulation, test the algorithm in 6 variations of the work environment, and analyze the test results. The genetic algorithm can determine the shortest path with 93% completeness among the 6 possible combinations of the start point, target point, and position of obstacles. The proposed GA, it can be argued, can be used to locate the shortest path in a warehouse with different start and end points.

A major challenge to the deployment of mobile robots is the ability to function autonomously, learning appropriate models for environmental features and adapting those models in response to environmental changes. This autonomous operation in turn requires autonomous selection/planning of an action sequence that facilitates learning and adaptation. Here we focus on color modeling/learning and analyze two algorithms that enable a mobile robot to plan action sequences that facilitate color learning: a long-term action selection approach that maximizes color learning opportunities while minimizing localization errors over an entire action sequence, and a greedy/heuristic action selection approach that plans incrementally, one step at a time, to maximize the benefits based on the current state of the world. The long-term action selection results in a more principled solution that requires minimal human supervision, while better failure recovery is achieved by incorporating features of the greedy planning approach. All algorithms are fully implemented and tested on the Sony AIBO robots.

Purpose The purpose of this paper is to consider the smooth path planning problem for a mobile robot based on the genetic algorithm (GA) and the Bezier curve. Design/methodology/approach The workspace of a mobile robot is described by a new grid-based representation that facilitates the operations of the adopted GA. The chromosome of the GA is composed of a sequence of binary numbered grids (i.e. control points of the Bezier curve). Ordinary genetic operators including crossover and mutation are used to search the optimum chromosome where the optimization criterion is the length of a piecewise collision-free Bezier curve path determined by the control points. Findings This paper has proposed a new smooth path planning for a mobile robot by resorting to the GA and the Bezier curve. A new grid-based representation of the workspace has been presented, which makes it convenient to perform operations in the GA. The GA has been used to search the optimum control points that determine the Bezier curve-based smooth path. The effectiveness of the proposed approach has been verified by a numerical experiment, and some performances of the obtained method have also been analyzed. Research limitations/implications There still remain many interesting topics, for example, how to solve the specific smooth path planning problem by using the GA and how to promote the computational efficiency in the more grids case. These issues deserve further research. Originality/value The purpose of this paper is to improve the existing results by making the following three distinctive contributions: a rigorous mathematical formulation of the path planning optimization problem is formulated; a general grid-based representation (2n × 2n) is proposed to describe the workspace of the mobile robots to facilitate the implementation of the GA where n is chosen according to the trade-off between the accuracy and the computational burden; and the control points of the Bezier curve are directly linked to the optimization criteria so that the generated paths are guaranteed to be optimal without any need for smoothing afterwards.

In mobile robot research domain and especially in its path planning sub-domain, the optimization tools the most used are PSO (Particle Swarm Optimization) and GA (Genetic Algorithms). In fact, mobile robot path planning is a multi-objective optimization problem where at least these objectives are considered: the shortest and the safest path to the goal. Sometimes other objectives are added like travel duration. The subject of this paper is a comparison investigation concerning the efficiency of PSO and GA in mobile robot path planning optimization. We start with a comparison of evolutionary performances of PSO and GA. Then, we apply PSO and GA in the optimization of parameters of DVSF\(^{2}\) (Dynamic Variable Speed Force Field) path planning approach. Different environments of different types, statics and dynamics are considered in these simulations to decide which is better for mobile robot path planning optimization: PSO or GA.

Skid-steered robots, with their robust structure and manoeuvrability, are generally used as outdoor mobile robots. Both kinematic and dynamic modelling of these robots is difficult due to sliding and rolling inherent in general curvilinear motion. In order to improve motion and pose estimation, this paper proposes a kinematic and dynamic model for skid-steered mobile robots. A PID controller, tuned using Genetic Algorithm, based on the dynamic model is then proposed for accurate control of the skid-steered robot. The dynamic model developed enables motion planning for general planar motion. The coefficient of rolling resistance, the coefficient of friction, and the shear deformation modulus, all of which have terrain-dependent values are accommodated in this model. Surveillance bots are of great importance in protecting and saving human life. In this context, mobile and multi-functional robots which map their surroundings are adopted as a means to reduce environmental restructuring and the number of devices used to cover a given area. Skid-steered robots are robust and, therefore, are ideal for surveillance applications.

Path planning problem of mobile robot is one that has intrigued and has received much attention throughout the history of robotics, since it is at the essence of what a mobile robot needs to be considered truly “autonomous”. A mobile robot must be able to find collision-free paths to move from one location to another, and in order to truly show a level of intelligence these paths must be optimized under some criteria that are important to the robot, working space and given problem. In this paper we propose a new structured multi-objective genetic algorithm to solve this problem. In our method we explore only valid search space that results in a smaller search space. Also we show the defect of earlier evaluation function and present a new evaluation function. To evaluate our idea we compare our evaluation function with other ones and show the performance of our method. Experiments show the ability of our method in finding best paths with low generation and population.

The paper studies the real-time stereo image-based localization of a vehicle in a prior 3D LiDAR map. A novel localization approach for mobile ground robot, which successfully combines conventional computer vision techniques, neural network based image analysis and numerical optimization, is proposed. It includes matching a noisy depth image and visible point cloud based on the modified Nelder-Mead optimization method. Deep neural network for image semantic segmentation is used to eliminate dynamic obstacles. The visible point cloud is extracted using a 3D mesh map representation. The proposed approach is evaluated on the KITTI dataset and a custom dataset collected from a ClearPath Husky mobile robot. It shows a stable absolute translation error of about 0.11 – 0.13 m. and a rotation error of 0.42 – 0.62 deg. The standard deviation of the obtained absolute metrics for our method is the smallest among other state-of-the-art approaches. Thus, our approach provides more stability in the estimated pose. It is achieved primarily through the use of multiple data frames during the optimization step and dynamic obstacles elimination on depth image. The method’s performance is demonstrated on different hardware platforms, including energy-efficient Nvidia Jetson Xavier AGX. With parallel code implementation, we achieve an input stereo image processing speed of 14 frames per second on Xavier AGX.